BibiGPT AI Video & Audio Summarizer MCP Server

OpenClaw / Claude Code / Codex Agent skill for summarizing videos/audio via BibiGPT CLI (bibi)

Local serverstdio

What is the BibiGPT AI Video & Audio Summarizer MCP server?

OpenClaw / Claude Code / Codex Agent skill for summarizing videos/audio via BibiGPT CLI (bibi). The bibigpt ai video & audio summarizer mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

AI Agent skill for summarizing videos, audio, and podcasts via BibiGPT.

Its toolset

Everything the assistant can do here goes through one of these:

  • summarize_video — Summarize a video or podcast URL
  • summarize_video_with_config — Summarize with custom prompt, model, language
  • summarize_by_chapter — Chapter-by-chapter summary
  • get_subtitle — Get transcript/subtitles with timestamps
  • create_summary_task — Create async task for long videos
  • get_task_status — Check async task status
  • OpenClaw — The OpenClaw tool exposed by this server
  • Commands — The Commands tool exposed by this server
  • Updating — BibiGPT ships three independently updateable layers. Pick the one that matches what you want refreshed
  • Cursor — Add to .cursor/mcp.json in project root, or configure in Cursor Settings → MCP:
  • Windsurf — The Windsurf tool exposed by this server
  • ChatGPT — 1. Settings → Apps & Connectors → Advanced settings → enable Developer mode 2. Settings → Apps & Connectors → Create connector 3. Enter URL

Configuration

You will need 2 environment variables: BIBIGPT_API_KEY, YOUR_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Adding it to your client

Installation goes through your MCP client rather than a global install: point it at skills on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

When to reach for it

Plenty of planning and project tracking servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. BibiGPT AI Video & Audio Summarizer's toolset — summarize_video, summarize_video_with_config, summarize_by_chapter and 11 more — is a fair guide to whether it matches your workflow. It is maintained by JimmyLv; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch BibiGPT AI Video & Audio Summarizer.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the bibigpt ai video & audio summarizer mcp server does with a few real requests.

Available tools

ToolWhat it does
summarize_videoSummarize a video or podcast URL
summarize_video_with_configSummarize with custom prompt, model, language
summarize_by_chapterChapter-by-chapter summary
get_subtitleGet transcript/subtitles with timestamps
create_summary_taskCreate async task for long videos
get_task_statusCheck async task status
OpenClawThe OpenClaw tool exposed by this server.
CommandsThe Commands tool exposed by this server.
UpdatingBibiGPT ships **three independently updateable layers**. Pick the one that matches what you want refreshed.
CursorAdd to .cursor/mcp.json in project root, or configure in Cursor Settings → MCP:
WindsurfThe Windsurf tool exposed by this server.
ChatGPT1. Settings → Apps & Connectors → Advanced settings → enable **Developer mode** 2. Settings → Apps & Connectors → **Create** connector 3. Enter URL: https://bibigpt.co/api/mcp 4. Complete OAuth authorization when prompte
ManusSettings → Connectors → Add Connectors → Custom MCP → +Add Custom MCP:
LobeChatSettings → Plugin Settings → Custom Plugins → Quick Import JSON:

How to install the BibiGPT AI Video & Audio Summarizer MCP server

{
  "mcpServers": {
    "bibigpt": {
      "type": "http",
      "url": "https://bibigpt.co/api/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
BIBIGPT_API_KEYCredential the server authenticates with.Yes
YOUR_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use BibiGPT AI Video & Audio Summarizer to summarize video.
  • Use BibiGPT AI Video & Audio Summarizer to summarize video with config.
  • Use BibiGPT AI Video & Audio Summarizer to summarize by chapter.

Frequently asked questions

It supports YouTube, podcasts, and other video/audio URLs. Local files are also supported.